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

    Neuronpedia

    INDEX
    Explanations

    warnings and advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .command
    -0.07
     nominee
    -0.07
     considered
    -0.07
     jj
    -0.07
    擾
    -0.07
    (t
    -0.07
     (<
    -0.07
    .Default
    -0.07
    jes
    -0.07
    outside
    -0.07
    POSITIVE LOGITS
     perplex
    0.08
     Parses
    0.08
     Müdürü
    0.07
    umph
    0.07
    想了
    0.07
     attn
    0.07
     Murder
    0.07
    พยายาม
    0.07
     wur
    0.07
     Suicide
    0.06
    Act Density 0.091%

    No Known Activations