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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     optimistic
    -0.10
     SCP
    -0.09
    ூர
    -0.08
     optimism
    -0.08
     физи
    -0.08
     ecological
    -0.08
     қар
    -0.07
    (protocol
    -0.07
     steril
    -0.07
     перспектив
    -0.07
    POSITIVE LOGITS
     표현
    0.09
    lera
    0.08
     Seite
    0.08
    kw
    0.08
     ṣ
    0.07
     despe
    0.07
     sige
    0.07
     Logo
    0.07
     rewritten
    0.07
     rename
    0.07
    Act Density 0.159%

    No Known Activations