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

    Neuronpedia

    INDEX
    Explanations

    stop at nothing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vie
    -0.07
    threat
    -0.07
    ुआत
    -0.06
    541
    -0.06
    including
    -0.06
     Superman
    -0.06
    Par
    -0.06
     التو
    -0.06
     PTSD
    -0.06
    ietf
    -0.06
    POSITIVE LOGITS
     Mỹ
    0.07
     λίγ
    0.06
     American
    0.06
     Fol
    0.06
     bereits
    0.06
     clown
    0.06
     boolean
    0.06
     shaded
    0.06
    止
    0.06
     gemeins
    0.06
    Act Density 0.020%

    No Known Activations