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

    Neuronpedia

    INDEX
    Explanations

    plus symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     через
    -0.06
     �
    -0.06
    .BAD
    -0.06
     entrar
    -0.06
    τρι
    -0.06
    .separator
    -0.06
     transporter
    -0.06
     Thin
    -0.06
    [end
    -0.05
     Leak
    -0.05
    POSITIVE LOGITS
    arris
    0.07
     тай
    0.07
     Important
    0.07
    نين
    0.07
     developments
    0.06
    цип
    0.06
     proposals
    0.06
    undi
    0.06
     etkin
    0.06
    .Threading
    0.06
    Act Density 0.004%

    No Known Activations