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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.59
     Chwiliwch
    -0.43
     baik
    -0.40
    >{@
    -0.39
     on
    -0.37
     with
    -0.36
     to
    -0.35
    rscheinlichkeit
    -0.35
     rosto
    -0.35
    stwa
    -0.35
    POSITIVE LOGITS
    ChildIndex
    0.77
     متعلقه
    0.71
     RSSSF
    0.70
    ruit
    0.66
    alyptus
    0.65
     تانيه
    0.65
    RUnlock
    0.62
     Simpli
    0.61
    Jeografia
    0.61
    utenant
    0.60
    Act Density 0.041%

    No Known Activations