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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     daar
    -0.07
    (mode
    -0.07
    (nombre
    -0.07
    Got
    -0.07
     ideological
    -0.06
     hurricanes
    -0.06
    -self
    -0.06
    appear
    -0.06
    ";}↵
    -0.06
    ('');↵
    -0.06
    POSITIVE LOGITS
    .tool
    0.07
    이라
    0.06
     BOOL
    0.06
     Ethan
    0.06
     العم
    0.06
     Mutation
    0.06
    _tt
    0.06
     Spotify
    0.06
     �
    0.06
     curse
    0.06
    Act Density 0.000%

    No Known Activations