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

    Neuronpedia

    INDEX
    Explanations

    ant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coer
    -0.06
     ERC
    -0.06
    ilitation
    -0.06
    -chat
    -0.06
     Threat
    -0.06
    orgia
    -0.06
    _EXPECT
    -0.06
     holog
    -0.06
     NAT
    -0.06
    storage
    -0.06
    POSITIVE LOGITS
     kiệm
    0.07
    (parse
    0.06
     тор
    0.06
    ีว
    0.06
    astes
    0.06
    尘
    0.06
     deals
    0.06
    Tyler
    0.06
     Modifier
    0.06
    ｧ
    0.06
    Act Density 0.009%

    No Known Activations