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

    Neuronpedia

    INDEX
    Explanations

    ed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    ไร
    -0.06
     didnt
    -0.06
     instability
    -0.06
     �
    -0.06
    ondheim
    -0.06
     hã
    -0.06
    世
    -0.06
    sWith
    -0.06
     сол
    -0.06
    POSITIVE LOGITS
     campaigners
    0.07
    _BLK
    0.07
    36
    0.06
    (typ
    0.06
    .success
    0.06
    beautiful
    0.06
    oplevel
    0.06
     KR
    0.06
     Segment
    0.06
    _TC
    0.06
    Act Density 0.000%

    No Known Activations