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

    Neuronpedia

    INDEX
    Explanations

    Juice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Merkezi
    -0.08
    TK
    -0.07
     ян
    -0.07
    .*;
↵
↵
    -0.06
    ((*
    -0.06
    ByEmail
    -0.06
     Nadu
    -0.06
    NSSet
    -0.06
     zim
    -0.06
    _axis
    -0.06
    POSITIVE LOGITS
    others
    0.07
     FILTER
    0.06
     depicting
    0.06
    :↵
    0.06
     happens
    0.06
    -group
    0.06
     group
    0.06
     if
    0.06
     pertaining
    0.06
     trenches
    0.06
    Act Density 0.155%

    No Known Activations