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

    Neuronpedia

    INDEX
    Explanations

    varied text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bew
    -0.07
    chematic
    -0.06
    _／
    -0.06
    3
    -0.06
    _T
    -0.06
     水
    -0.06
    _Input
    -0.06
    constraints
    -0.06
    müş
    -0.06
    .Sc
    -0.06
    POSITIVE LOGITS
     إليه
    0.07
    -terrorism
    0.07
    ampo
    0.06
     recogn
    0.06
     ALPHA
    0.06
    observeOn
    0.06
     universal
    0.06
     най
    0.06
    _commit
    0.06
     grip
    0.06
    Act Density 0.000%

    No Known Activations