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

    Neuronpedia

    INDEX
    Explanations

    inherent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ascii
    -0.07
     hurried
    -0.07
     stimulated
    -0.07
     subsidized
    -0.07
     railways
    -0.07
     bestellen
    -0.07
     division
    -0.07
    cancelled
    -0.07
    .Orientation
    -0.07
     murderers
    -0.07
    POSITIVE LOGITS
     inherent
    0.17
     inherently
    0.14
    herent
    0.09
     dormant
    0.07
    Indent
    0.06
    .Here
    0.06
    .send
    0.06
    _child
    0.06
    arent
    0.06
    _Property
    0.06
    Act Density 0.004%

    No Known Activations