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

    Neuronpedia

    INDEX
    Explanations

    effects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vill
    -0.07
     blockbuster
    -0.07
     Nightmare
    -0.07
     Gardner
    -0.07
     Partition
    -0.07
    _di
    -0.07
    (木
    -0.07
     flowing
    -0.07
     equilibrium
    -0.07
     Sister
    -0.06
    POSITIVE LOGITS
     effects
    0.06
    マ
    0.06
    @a
    0.06
     salt
    0.06
    mo
    0.06
     Affordable
    0.06
     objev
    0.05
    vů
    0.05
    kB
    0.05
    .Java
    0.05
    Act Density 0.009%

    No Known Activations