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

    Neuronpedia

    INDEX
    Explanations

    methods or solutions documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     validation
    -0.07
    "B
    -0.06
    "F
    -0.06
     PASSWORD
    -0.06
    .reload
    -0.06
     gridBagConstraints
    -0.06
    dm
    -0.06
     packs
    -0.06
    .imp
    -0.06
     betrayal
    -0.06
    POSITIVE LOGITS
     Monterey
    0.07
     miscar
    0.07
    apeut
    0.07
     اسر
    0.07
    χν
    0.06
     Ré
    0.06
     Eine
    0.06
    sect
    0.06
     Aust
    0.06
     Horizon
    0.06
    Act Density 0.009%

    No Known Activations