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

    Neuronpedia

    INDEX
    Explanations

    melon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ticket
    -0.07
    AffineTransform
    -0.07
     Ward
    -0.07
    _third
    -0.07
    segment
    -0.07
     ticket
    -0.07
    _logits
    -0.07
     Tro
    -0.07
    _family
    -0.07
    声
    -0.07
    POSITIVE LOGITS
     influencing
    0.07
    enso
    0.07
    pping
    0.07
     impacts
    0.07
     donne
    0.07
    anol
    0.06
    させて頂
    0.06
    צפון
    0.06
    _DSP
    0.06
     על
    0.06
    Act Density 0.001%

    No Known Activations