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

    Neuronpedia

    INDEX
    Explanations

    Code and technical errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scrut
    -0.07
    levard
    -0.07
    쨩
    -0.07
    ELS
    -0.06
    Library
    -0.06
     evidence
    -0.06
    选�
    -0.06
     Sports
    -0.06
     Babe
    -0.06
    꽃
    -0.06
    POSITIVE LOGITS
    固定资产
    0.07
    遗漏
    0.07
    _encode
    0.07
     disappoint
    0.07
     risky
    0.07
    准时
    0.07
    为代表的
    0.07
    华北
    0.07
    _APPLICATION
    0.07
    appointment
    0.07
    Act Density 0.000%

    No Known Activations