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

    Neuronpedia

    INDEX
    Explanations

    Middle of texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ake
    -0.07
     orthogonal
    -0.07
     martial
    -0.06
     Professor
    -0.06
     술
    -0.06
     rooted
    -0.06
    =P
    -0.06
     Cultural
    -0.06
    _linear
    -0.06
    Strip
    -0.06
    POSITIVE LOGITS
    HCI
    0.06
    placeholder
    0.06
    .integration
    0.06
    urgery
    0.06
    _STRUCTURE
    0.06
    leme
    0.06
    CG
    0.06
    bcrypt
    0.06
    storms
    0.06
    employed
    0.06
    Act Density 0.008%

    No Known Activations