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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     needy
    -0.07
    園
    -0.07
     creepy
    -0.07
    并向
    -0.07
    ?)↵↵
    -0.07
    해서
    -0.06
    eden
    -0.06
     (++
    -0.06
    bi
    -0.06
    .stereotype
    -0.06
    POSITIVE LOGITS
     entities
    0.08
    OO
    0.07
    暫
    0.07
    _ISS
    0.07
     człowie
    0.07
    年人
    0.06
     Nacional
    0.06
     nature
    0.06
    .getAccount
    0.06
    TT
    0.06
    Act Density 0.001%

    No Known Activations