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

    Neuronpedia

    INDEX
    Explanations

    working

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    querque
    -0.07
    _elt
    -0.07
    ("""
    -0.07
    combo
    -0.06
    (Profile
    -0.06
     seksi
    -0.06
    SubMenu
    -0.06
    .Ex
    -0.06
     🙂↵↵
    -0.06
     newPassword
    -0.06
    POSITIVE LOGITS
     sch
    0.06
    feat
    0.06
    Target
    0.06
     κρα
    0.06
     pressed
    0.06
     proced
    0.06
    ONUS
    0.06
    /power
    0.06
     assemble
    0.06
     Crusher
    0.06
    Act Density 0.000%

    No Known Activations