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

    Neuronpedia

    INDEX
    Explanations

    outside

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    correct
    -0.07
    exo
    -0.07
    _char
    -0.07
     interpret
    -0.07
    _filt
    -0.07
     Added
    -0.06
     explorer
    -0.06
     вис
    -0.06
     infect
    -0.06
     vital
    -0.06
    POSITIVE LOGITS
     useForm
    0.06
    alsy
    0.06
     jsx
    0.06
    .MouseEventHandler
    0.06
     onFinish
    0.06
    lake
    0.06
    ck
    0.06
     chatter
    0.06
    (){}↵
    0.06
     jenom
    0.06
    Act Density 0.005%

    No Known Activations