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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     बल
    -0.08
    ')}}
    -0.07
    .Diff
    -0.07
    _CONV
    -0.07
    .Username
    -0.07
    .birth
    -0.07
    .Free
    -0.07
    (face
    -0.06
    	spec
    -0.06
    _DR
    -0.06
    POSITIVE LOGITS
    �
    0.07
     firewall
    0.07
    invest
    0.06
    Expl
    0.06
    Validator
    0.06
    Todo
    0.06
     guide
    0.06
     doğr
    0.06
    asion
    0.06
     झ
    0.06
    Act Density 0.003%

    No Known Activations