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

    Neuronpedia

    INDEX
    Explanations

    Semantics and language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     colourful
    -0.07
    .keras
    -0.06
    �
    -0.06
    	rd
    -0.06
    ５
    -0.06
    かな
    -0.06
     Cottage
    -0.06
     Viol
    -0.06
    β
    -0.06
     nạn
    -0.06
    POSITIVE LOGITS
    0.07
     Sheriff
    0.07
     SEC
    0.07
     checkpoints
    0.07
    Jeff
    0.07
     beacon
    0.06
     Assembly
    0.06
    احث
    0.06
     Merkel
    0.06
    .store
    0.06
    Act Density 0.000%

    No Known Activations