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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shower
    -0.07
    .phase
    -0.06
    _cpus
    -0.06
     IDb
    -0.06
     Valve
    -0.06
     porch
    -0.06
     consts
    -0.06
     thrust
    -0.06
    ざ
    -0.06
     Shower
    -0.06
    POSITIVE LOGITS
     Asi
    0.07
     erk
    0.07
    误
    0.07
     genetic
    0.07
    "]=="
    0.06
    ARK
    0.06
    reh
    0.06
    773
    0.06
    onation
    0.06
    彡
    0.06
    Act Density 0.002%

    No Known Activations