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

    Neuronpedia

    INDEX
    Explanations

    safety dangers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -health
    -0.08
    <List
    -0.07
    剑
    -0.07
    .evaluate
    -0.07
     jejím
    -0.06
    igin
    -0.06
     죽
    -0.06
    ,),↵
    -0.06
     health
    -0.06
     Bu
    -0.06
    POSITIVE LOGITS
     Washer
    0.06
    bilder
    0.06
    _PUSHDATA
    0.06
    FirstResponder
    0.06
    >()->
    0.06
    EMAIL
    0.06
     strdup
    0.06
    printing
    0.06
     finding
    0.06
    (mapStateToProps
    0.06
    Act Density 0.044%

    No Known Activations