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

    Neuronpedia

    INDEX
    Explanations

    ~/

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :-
    -0.07
    ﺄ
    -0.06
    _Title
    -0.06
    (PARAM
    -0.06
    𝚆
    -0.06
     Leaves
    -0.06
     disagree
    -0.06
    ῷ
    -0.06
     Está
    -0.06
    ')↵
    -0.06
    POSITIVE LOGITS
    .quick
    0.07
     треб
    0.07
    irical
    0.07
    .Creator
    0.07
     decentralized
    0.07
    _rat
    0.07
    feat
    0.07
     lasting
    0.07
    iforn
    0.07
     ב
    0.07
    Act Density 0.002%

    No Known Activations