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

    Neuronpedia

    INDEX
    Explanations

    notice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cpus
    -0.08
    -_
    -0.07
    OTH
    -0.07
    량
    -0.06
    }$
    -0.06
    [Y
    -0.06
    _Y
    -0.06
     Crate
    -0.06
     shocks
    -0.06
     theirs
    -0.06
    POSITIVE LOGITS
    _firstname
    0.07
    :"",
    0.07
    wish
    0.07
    ープ
    0.06
    νει
    0.06
     ⌒
    0.06
     náz
    0.06
    едж
    0.06
    Shar
    0.06
     нали
    0.06
    Act Density 0.003%

    No Known Activations