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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _INITIAL
    -0.08
    ้ม
    -0.07
    .BAD
    -0.07
    [#
    -0.07
    afx
    -0.06
    یست
    -0.06
    �
    -0.06
    _pick
    -0.06
    &M
    -0.06
     beforehand
    -0.06
    POSITIVE LOGITS
     village
    0.07
    ]‏
    0.07
    .row
    0.07
     airst
    0.06
     resc
    0.06
     suburb
    0.06
     acknowledgement
    0.06
     town
    0.06
    χ
    0.06
     rushes
    0.06
    Act Density 0.002%

    No Known Activations