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

    Neuronpedia

    INDEX
    Explanations

    close/dispose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FlatButton
    -0.07
     holds
    -0.07
    ());
↵
    -0.06
     metrics
    -0.06
    ullets
    -0.06
     Maher
    -0.06
     свят
    -0.06
     stomach
    -0.06
    (title
    -0.06
     satire
    -0.06
    POSITIVE LOGITS
    μον
    0.06
    亡
    0.06
     CType
    0.06
     appropriated
    0.06
    ask
    0.06
     disclosed
    0.06
     ensuing
    0.06
    hip
    0.06
    lotte
    0.06
     possessions
    0.06
    Act Density 0.005%

    No Known Activations