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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shock
    -0.08
     обол
    -0.07
     attire
    -0.06
     ва
    -0.06
     burner
    -0.06
    -close
    -0.06
    However
    -0.06
     zus
    -0.06
     onemocnění
    -0.06
     河
    -0.06
    POSITIVE LOGITS
     Meat
    0.07
     liebe
    0.06
     ${({
    0.06
    .Unknown
    0.05
    verification
    0.05
    Muslim
    0.05
    がない
    0.05
    ￣￣￣￣
    0.05
    す
    0.05
    (newState
    0.05
    Act Density 0.005%

    No Known Activations