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

    Neuronpedia

    INDEX
    Explanations

    Date ranges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -functional
    -0.07
    Approval
    -0.07
    heads
    -0.06
     Finger
    -0.06
    _ANAL
    -0.06
    Et
    -0.06
    ocused
    -0.06
     Morph
    -0.06
    Що
    -0.06
     seekers
    -0.06
    POSITIVE LOGITS
     vectors
    0.07
     delights
    0.06
     Lager
    0.06
     Composer
    0.06
     marzo
    0.06
    /single
    0.06
     борь
    0.06
     Drawing
    0.06
    ty
    0.06
    Jun
    0.06
    Act Density 0.022%

    No Known Activations