Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Non-English languages

    np_max-act · gemini-2.0-flash

    The neuron specifically lights up on Russian present-tense verb forms (e.g. бежит, летит, несёт) within Cyrillic text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     feats
    -0.06
    筒
    -0.06
    _opcode
    -0.06
     comedy
    -0.06
    gtest
    -0.06
    _BOOLEAN
    -0.06
     windowHeight
    -0.06
    amping
    -0.06
    intestinal
    -0.06
     dips
    -0.06
    POSITIVE LOGITS
    );
↵
↵
    0.07
    レット
    0.07
     повинна
    0.07
     Svět
    0.06
     Blog
    0.06
     staggering
    0.06
     Inv
    0.06
     буде
    0.06
     referencing
    0.06
     Carousel
    0.06
    Act Density 0.040%

    No Known Activations