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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JOB
    -0.07
     Kindle
    -0.07
     История
    -0.06
    بين
    -0.06
    oscopic
    -0.06
     Numero
    -0.06
    غات
    -0.06
     mondo
    -0.06
    ijk
    -0.06
    DOC
    -0.06
    POSITIVE LOGITS
     prt
    0.07
     Gab
    0.07
     krit
    0.07
    �
    0.06
     STDERR
    0.06
     frowned
    0.06
    [P
    0.06
    €
    0.06
    verbose
    0.06
     pri
    0.06
    Act Density 0.068%

    No Known Activations