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

    Neuronpedia

    INDEX
    Explanations

    -minded

    np_max-act · gemini-2.0-flash

    The neuron never activates—it does not detect any particular token or pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .buffer
    -0.08
     извест
    -0.07
    Tester
    -0.07
     větš
    -0.07
     elast
    -0.06
     Lens
    -0.06
    に入
    -0.06
     ersten
    -0.06
     preparations
    -0.06
     großen
    -0.06
    POSITIVE LOGITS
     كس
    0.07
    _ADMIN
    0.07
     SignUp
    0.07
    Fish
    0.06
     》
    0.06
     chmod
    0.06
    yl
    0.06
    ≠
    0.06
     cry
    0.06
     AD
    0.06
    Act Density 0.011%

    No Known Activations