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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     progressBar
    -0.06
    .containsKey
    -0.06
    OLON
    -0.06
    .navigator
    -0.06
     legendary
    -0.06
    izio
    -0.06
    .assertNotNull
    -0.06
     الض
    -0.06
    .all
    -0.06
    _None
    -0.06
    POSITIVE LOGITS
     Marcus
    0.07
     protects
    0.06
     beats
    0.06
    Marcus
    0.06
     chamber
    0.06
     generous
    0.06
     serve
    0.06
    Unity
    0.06
    >)
    0.06
     :/
    0.06
    Act Density 0.063%

    No Known Activations