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

    Neuronpedia

    INDEX
    Explanations

    Hess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amera
    -0.06
     아직
    -0.06
     �
    -0.06
    �택
    -0.06
    _FAR
    -0.06
     �
    -0.06
     yüz
    -0.06
    .track
    -0.05
    lz
    -0.05
    .userData
    -0.05
    POSITIVE LOGITS
     Hess
    0.18
    essian
    0.13
     etwa
    0.11
    ess
    0.10
    ipro
    0.10
    ESS
    0.09
    esse
    0.09
     кле
    0.08
    Важ
    0.07
     Neck
    0.07
    Act Density 0.003%

    No Known Activations