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

    Neuronpedia

    INDEX
    Explanations

    mathematical reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Writer
    -0.09
     oka
    -0.08
    opcode
    -0.08
    _writer
    -0.08
    ställ
    -0.08
    ',['
    -0.08
    publisher
    -0.08
     χει
    -0.07
    ssid
    -0.07
    tracks
    -0.07
    POSITIVE LOGITS
     individually
    0.16
     Individ
    0.14
    Individual
    0.11
     Individual
    0.11
     individuelles
    0.10
     individ
    0.10
     individuais
    0.09
     individuales
    0.09
     afzonder
    0.09
     themselves
    0.09
    Act Density 0.033%

    No Known Activations