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

    Neuronpedia

    INDEX
    Explanations

    VRF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ніч
    -0.07
     Write
    -0.07
    аном
    -0.07
    .Library
    -0.07
     kHz
    -0.07
    hz
    -0.07
    /Create
    -0.07
    /team
    -0.06
    _latency
    -0.06
    št
    -0.06
    POSITIVE LOGITS
     demonstrates
    0.07
    _Il
    0.06
     hindi
    0.06
     Confirm
    0.06
    ,[
    0.06
    cwd
    0.06
     getPassword
    0.06
    ığ
    0.06
     nicely
    0.06
    !↵
    0.06
    Act Density 0.000%

    No Known Activations