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

    Neuronpedia

    INDEX
    Explanations

    _posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    768
    -0.07
    nP
    -0.07
     warrant
    -0.06
    (typ
    -0.06
    hh
    -0.06
     correl
    -0.06
     Germany
    -0.06
    level
    -0.06
    .quality
    -0.06
     cured
    -0.06
    POSITIVE LOGITS
    erez
    0.07
    liked
    0.07
    (ALOAD
    0.06
     ensured
    0.06
    .setAction
    0.06
    ohan
    0.06
     derece
    0.06
     Specifications
    0.06
     ischem
    0.06
     Jurassic
    0.06
    Act Density 0.000%

    No Known Activations