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

    Neuronpedia

    INDEX
    Explanations

    iteration parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CppGeneric
    -0.06
    uite
    -0.06
    Voltage
    -0.06
     part
    -0.06
    ’int
    -0.06
     potent
    -0.06
    wargs
    -0.06
    krom
    -0.06
    ATTRIBUTE
    -0.05
    Port
    -0.05
    POSITIVE LOGITS
     compilation
    0.07
    ूड
    0.06
    ển
    0.06
     Identification
    0.06
     trespass
    0.06
    Studio
    0.06
    먹
    0.06
     Muj
    0.06
    шая
    0.06
    (effect
    0.06
    Act Density 0.025%

    No Known Activations