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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    éf
    -0.06
    -making
    -0.06
    Def
    -0.06
     Bec
    -0.06
     digest
    -0.06
     '\\
    -0.06
     fins
    -0.06
    _Variable
    -0.06
    shell
    -0.06
    状态
    -0.06
    POSITIVE LOGITS
     başka
    0.07
     railing
    0.07
    نام
    0.07
     конт
    0.06
    lanır
    0.06
    "/>.</
    0.06
     Direct
    0.06
     enlist
    0.06
    pees
    0.06
     LNG
    0.06
    Act Density 0.036%

    No Known Activations