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

    Neuronpedia

    INDEX
    Explanations

    middle index

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .servers
    -0.07
     wasn
    -0.06
    	B
    -0.06
     Julia
    -0.06
    jq
    -0.06
     Monica
    -0.06
     insists
    -0.06
    ляют
    -0.06
    BBBB
    -0.06
     savoir
    -0.06
    POSITIVE LOGITS
    toFloat
    0.07
    (xml
    0.07
     predis
    0.07
     spinach
    0.06
    (Matrix
    0.06
    _Profile
    0.06
     муницип
    0.06
    903
    0.06
     προ
    0.06
    explo
    0.06
    Act Density 0.003%

    No Known Activations