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

    Neuronpedia

    INDEX
    Explanations

    Living/surviving conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ved
    -0.09
    "+↵
    -0.07
     grpc
    -0.07
    python
    -0.07
    weakSelf
    -0.06
     mysqli
    -0.06
    

↵
    -0.06
    <?>
    -0.06
     malloc
    -0.06
    opes
    -0.06
    POSITIVE LOGITS
     rallies
    0.07
    YOU
    0.06
    霈
    0.06
    You
    0.06
    Articles
    0.06
    アウ
    0.06
    secs
    0.06
    Battle
    0.06
     hunts
    0.06
    搶
    0.06
    Act Density 0.255%

    No Known Activations