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

    Neuronpedia

    INDEX
    Explanations

    em

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vill
    -0.07
    _ISS
    -0.07
     HOR
    -0.06
    �
    -0.06
    991
    -0.06
     IReadOnly
    -0.06
     Vill
    -0.06
     Banana
    -0.06
    943
    -0.06
    含
    -0.06
    POSITIVE LOGITS
     em
    0.08
     Emmy
    0.08
     escape
    0.08
     Em
    0.07
     amenities
    0.07
    /em
    0.07
    _em
    0.07
     Emil
    0.07
    Equal
    0.07
    mc
    0.07
    Act Density 0.070%

    No Known Activations