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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rets
    -0.07
     prizes
    -0.07
    英文
    -0.06
     Lun
    -0.06
     xd
    -0.06
    㬎
    -0.06
     entrusted
    -0.06
    pret
    -0.06
    eller
    -0.06
     devil
    -0.06
    POSITIVE LOGITS
     Actions
    0.08
    айте
    0.07
    �
    0.07
     iPad
    0.07
     Raider
    0.07
     Cors
    0.07
    MORE
    0.07
    Cou
    0.07
    Barrier
    0.07
    Navig
    0.06
    Act Density 0.042%

    No Known Activations