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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ign
    -0.07
    _locked
    -0.06
    Lots
    -0.06
     치
    -0.06
     près
    -0.06
     ImVec
    -0.06
     cient
    -0.06
     Template
    -0.06
    _PP
    -0.06
     peaked
    -0.06
    POSITIVE LOGITS
    _l
    0.07
     textures
    0.07
    暴
    0.07
    ]-
    0.06
    adır
    0.06
    _ID
    0.06
     detect
    0.06
    vid
    0.06
     Â
    0.06
    _by
    0.06
    Act Density 1.067%

    No Known Activations