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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     envelop
    -0.09
     ornate
    -0.09
     flot
    -0.08
     Electric
    -0.08
     Envelope
    -0.08
     bloginfo
    -0.08
    plosion
    -0.08
     değer
    -0.08
     Popup
    -0.08
     मस
    -0.08
    POSITIVE LOGITS
     undefeated
    0.12
     tally
    0.12
     victories
    0.11
     જીત
    0.11
     contabil
    0.11
     achievements
    0.11
     accomplishments
    0.10
     successes
    0.10
    _counts
    0.10
    .count
    0.10
    Act Density 0.024%

    No Known Activations