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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .PUT
    -0.06
     Bottom
    -0.06
    низ
    -0.06
    /password
    -0.06
    대표
    -0.06
     خوبی
    -0.06
     دو
    -0.06
    _ICON
    -0.06
    ими
    -0.06
     خلق
    -0.06
    POSITIVE LOGITS
    olvers
    0.07
    fat
    0.06
     expression
    0.06
     vase
    0.06
     Socket
    0.06
    commission
    0.06
    ังส
    0.06
     emission
    0.06
     mech
    0.06
     commission
    0.06
    Act Density 0.000%

    No Known Activations