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

    Neuronpedia

    INDEX
    Explanations

    Pulitzer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    111
    -0.06
    ũ
    -0.06
     DLC
    -0.06
    IAN
    -0.06
    /ns
    -0.06
    -ac
    -0.06
    社
    -0.06
     NAS
    -0.06
     impl
    -0.06
    shm
    -0.06
    POSITIVE LOGITS
     blood
    0.07
     Minimum
    0.07
     getName
    0.07
    ])))↵
    0.07
    уючи
    0.07
     gag
    0.06
     animated
    0.06
    Overlay
    0.06
    _mv
    0.06
     egal
    0.06
    Act Density 0.000%

    No Known Activations