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

    Neuronpedia

    INDEX
    Explanations

    Cannot make any guessesby

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     positivity
    -0.08
    FTWARE
    -0.07
    INET
    -0.07
    .languages
    -0.07
    owania
    -0.07
     AMS
    -0.07
     часом
    -0.07
     IAM
    -0.06
    ルク
    -0.06
     SCT
    -0.06
    POSITIVE LOGITS
     �
    0.07
     όπως
    0.07
    Annotation
    0.06
    에
    0.06
     нарез
    0.06
    .Alignment
    0.06
     gid
    0.06
     δι
    0.06
     roma
    0.06
     좋
    0.06
    Act Density 0.000%

    No Known Activations