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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FW
    -0.07
    ()</
    -0.07
    -warning
    -0.06
     pepper
    -0.06
     Nope
    -0.06
    ("""↵
    -0.06
    ύ
    -0.06
     @{
    -0.06
    ignet
    -0.06
    >All
    -0.06
    POSITIVE LOGITS
     sprint
    0.07
     inconsistency
    0.06
    \Extension
    0.06
     MATCH
    0.06
     afford
    0.06
     Sprint
    0.06
    拓
    0.06
     대행
    0.05
     Mush
    0.05
     unint
    0.05
    Act Density 0.194%

    No Known Activations