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

    Neuronpedia

    INDEX
    Explanations

    syntax characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gy
    -0.06
     Hun
    -0.06
    utions
    -0.06
    Van
    -0.06
    핧
    -0.06
    ってくる
    -0.06
    Sad
    -0.06
    巽
    -0.06
     Reload
    -0.06
     אלק
    -0.06
    POSITIVE LOGITS
    core
    0.07
    首相
    0.07
     routines
    0.07
    _ix
    0.07
    .commons
    0.07
     KEEP
    0.07
    .document
    0.07
    Perfect
    0.06
     strive
    0.06
    kea
    0.06
    Act Density 0.036%

    No Known Activations