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

    Neuronpedia

    INDEX
    Explanations

    95

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ierte
    -0.08
    SIM
    -0.07
    asso
    -0.07
     totaling
    -0.06
    belie
    -0.06
    إ
    -0.06
     başlan
    -0.06
    ССР
    -0.06
    Blockly
    -0.06
     Alam
    -0.06
    POSITIVE LOGITS
    95
    0.07
    093
    0.07
    095
    0.07
    091
    0.07
    689
    0.07
    :^(
    0.06
    (resp
    0.06
    932
    0.06
     вок
    0.06
    _handles
    0.06
    Act Density 0.003%

    No Known Activations