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

    Neuronpedia

    INDEX
    Explanations

    scratch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Marg
    -0.07
    _MODAL
    -0.07
     release
    -0.06
    dim
    -0.06
    elta
    -0.06
    lda
    -0.06
    _lin
    -0.06
     condol
    -0.06
    partition
    -0.06
    Fal
    -0.06
    POSITIVE LOGITS
     scratch
    0.08
     Skills
    0.07
     значення
    0.07
    uther
    0.06
     Scratch
    0.06
    0.06
     distinctly
    0.06
     truncate
    0.06
     createdAt
    0.06
     psychologically
    0.06
    Act Density 0.003%

    No Known Activations