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

    Neuronpedia

    INDEX
    Explanations

    German text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     honestly
    -0.07
    .COLUMN
    -0.07
    ovation
    -0.07
     wrestler
    -0.07
    .’↵↵
    -0.06
    간
    -0.06
     pleasures
    -0.06
     exploring
    -0.06
    Van
    -0.06
    ."↵
    -0.06
    POSITIVE LOGITS
    _pg
    0.07
    โล
    0.06
     Abort
    0.06
     PF
    0.06
     reconnect
    0.06
    Tick
    0.06
     inhib
    0.06
     рав
    0.06
     binds
    0.06
     обеспечива
    0.06
    Act Density 0.053%

    No Known Activations