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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .::
    -0.08
    65
    -0.07
    Free
    -0.07
    066
    -0.06
    leting
    -0.06
     editar
    -0.06
    75
    -0.06
     starvation
    -0.06
    igrants
    -0.06
     Wizard
    -0.06
    POSITIVE LOGITS
     [
    0.16
    [
    0.13
     [↵
    0.10
     [\
    0.10
     [_
    0.10
     [[
    0.09
    [B
    0.09
     [-
    0.09
     […
    0.09
    _[
    0.09
    Act Density 0.324%

    No Known Activations