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

    Neuronpedia

    INDEX
    Explanations

    galaxy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    వ
    -0.08
    船只
    -0.07
     которым
    -0.07
     worker
    -0.07
     deed
    -0.07
     seem
    -0.07
    _lens
    -0.07
    Two
    -0.07
    此人
    -0.07
     lodging
    -0.07
    POSITIVE LOGITS
     sexy
    0.08
    ket
    0.08
    铝合金
    0.08
    /routes
    0.07
    ITED
    0.07
     hinter
    0.07
     intrigued
    0.07
     חשוב
    0.07
     princess
    0.07
    _inches
    0.07
    Act Density 0.019%

    No Known Activations