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

    Neuronpedia

    INDEX
    Explanations

    component

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .total
    -0.07
     incomes
    -0.07
    :test
    -0.07
     police
    -0.07
    _flight
    -0.06
     PTSD
    -0.06
    ']
    -0.06
    .IGNORE
    -0.06
     altogether
    -0.06
     rob
    -0.06
    POSITIVE LOGITS
    _lot
    0.06
     '\
    0.06
     раб
    0.06
    antor
    0.06
    áři
    0.06
    ipsoid
    0.06
     história
    0.06
     tip
    0.06
    toolbar
    0.06
     сент
    0.05
    Act Density 0.001%

    No Known Activations