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

    Neuronpedia

    INDEX
    Explanations

    Formal/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nuevas
    -0.07
     zwe
    -0.07
    вер
    -0.06
     unethical
    -0.06
     doen
    -0.06
    upa
    -0.06
    atars
    -0.06
    SX
    -0.06
    cj
    -0.06
     býval
    -0.06
    POSITIVE LOGITS
    �
    0.07
    .req
    0.07
     Near
    0.06
    thane
    0.06
     specialists
    0.06
    _hs
    0.06
     регуляр
    0.06
     Dhabi
    0.06
    odian
    0.06
    703
    0.06
    Act Density 0.000%

    No Known Activations