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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Probe
    -0.07
    摇
    -0.07
    .RIGHT
    -0.06
    ]:
    -0.06
     decoding
    -0.06
     maximal
    -0.06
    /io
    -0.06
    HOLDER
    -0.06
    _compute
    -0.06
     Sunni
    -0.06
    POSITIVE LOGITS
     EMAIL
    0.08
     utan
    0.07
     RCA
    0.06
     Romania
    0.06
     milano
    0.06
     Brazil
    0.06
     �
    0.06
     Rol
    0.06
    Om
    0.06
     noi
    0.06
    Act Density 0.179%

    No Known Activations