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

    Neuronpedia

    INDEX
    Explanations

    fishing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voltage
    -0.07
    BYTE
    -0.07
     detectors
    -0.07
    Detection
    -0.07
     zeroes
    -0.06
     Bird
    -0.06
    Language
    -0.06
     debug
    -0.06
     yuan
    -0.06
     detector
    -0.06
    POSITIVE LOGITS
    orary
    0.08
     piş
    0.06
     Pra
    0.06
     Appalach
    0.06
    adece
    0.06
     παρ
    0.06
    azed
    0.06
    igrated
    0.06
     grantResults
    0.06
     WAL
    0.06
    Act Density 0.016%

    No Known Activations