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

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     האינטרנט
    -0.07
    图像
    -0.07
    سار
    -0.06
    跟随
    -0.06
    ﾒ
    -0.06
    imos
    -0.06
    脑
    -0.06
    촌
    -0.06
    ושא
    -0.06
    𝒅
    -0.06
    POSITIVE LOGITS
     prized
    0.07
    CK
    0.07
    _SSL
    0.07
    SX
    0.07
    _fk
    0.07
     \$
    0.07
    REDIT
    0.07
    BundleOrNil
    0.07
     flipped
    0.07
     riê
    0.06
    Act Density 0.001%

    No Known Activations