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

    Neuronpedia

    INDEX
    Explanations

    fictional texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .encode
    -0.07
    ITE
    -0.07
    stud
    -0.07
    asto
    -0.07
     len
    -0.06
    receive
    -0.06
    cuda
    -0.06
     domicile
    -0.06
    peg
    -0.06
     especially
    -0.06
    POSITIVE LOGITS
     homelessness
    0.07
    -ignore
    0.07
    malıdır
    0.06
     Gardner
    0.06
     bodily
    0.06
     classname
    0.06
    _tc
    0.06
    Extensions
    0.06
    unct
    0.06
     esper
    0.05
    Act Density 0.040%

    No Known Activations