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

    Neuronpedia

    INDEX
    Explanations

    balance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ascending
    -0.07
    .Context
    -0.06
    240
    -0.06
    wan
    -0.06
     Thou
    -0.06
    models
    -0.06
    zza
    -0.06
    loe
    -0.06
    validate
    -0.06
     Sala
    -0.06
    POSITIVE LOGITS
     παρ
    0.08
     zel
    0.07
     stash
    0.06
     مج
    0.06
     Tamb
    0.06
     종
    0.06
     kulak
    0.06
     reserves
    0.06
    658
    0.06
     अद
    0.06
    Act Density 0.034%

    No Known Activations