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

    Neuronpedia

    INDEX
    Explanations

    Scientific/Mathematical Notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eniable
    -0.07
    웬
    -0.07
    grese
    -0.07
    forgettable
    -0.07
     derives
    -0.07
     empleado
    -0.07
    }')↵
    -0.07
    ureen
    -0.07
    (date
    -0.07
    자를
    -0.07
    POSITIVE LOGITS
    Beam
    0.08
    _max
    0.07
    妓
    0.07
     onward
    0.07
    OFF
    0.06
    🠳
    0.06
     addiction
    0.06
    IOD
    0.06
    Method
    0.06
    楽
    0.06
    Act Density 0.014%

    No Known Activations