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

    Neuronpedia

    INDEX
    Explanations

    result

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     de
    -0.08
     вполне
    -0.08
    👘
    -0.08
    契合
    -0.08
    何度も
    -0.08
     overthrow
    -0.08
     of
    -0.08
    🍔
    -0.08
    icontains
    -0.07
     Harmony
    -0.07
    POSITIVE LOGITS
     sources
    0.07
     Proposition
    0.07
    anus
    0.07
     ils
    0.07
    zer
    0.07
     finding
    0.07
    Rotor
    0.06
     résultats
    0.06
     succ
    0.06
    مراكز
    0.06
    Act Density 0.025%

    No Known Activations