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

    Neuronpedia

    INDEX
    Explanations

    wide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cap
    -0.07
    ibe
    -0.07
     initially
    -0.07
     П
    -0.06
    iven
    -0.06
    оу
    -0.06
     Exc
    -0.06
    /access
    -0.06
    ("---
    -0.06
     活
    -0.06
    POSITIVE LOGITS
    .getLongitude
    0.06
     sklearn
    0.06
     sho
    0.06
    τή
    0.06
    _fd
    0.06
     موجب
    0.06
    SYM
    0.06
    .Sprintf
    0.05
     cunning
    0.05
     stained
    0.05
    Act Density 0.034%

    No Known Activations