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

    Neuronpedia

    INDEX
    Explanations

    periods/cycles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Bold
    -0.08
     politic
    -0.08
     jól
    -0.08
    .Completed
    -0.07
    “La
    -0.07
     cuộc
    -0.07
     Simpl
    -0.07
     Fic
    -0.07
    imental
    -0.07
    Completed
    -0.07
    POSITIVE LOGITS
     arrests
    0.08
     orbit
    0.08
     pertence
    0.08
     perten
    0.08
     hashed
    0.08
     kidnapping
    0.08
     visitante
    0.08
    hooks
    0.07
    avera
    0.07
     reachable
    0.07
    Act Density 0.007%

    No Known Activations