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

    Neuronpedia

    INDEX
    Explanations

    Guy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eld
    -0.06
     Belfast
    -0.06
     Har
    -0.06
    .Login
    -0.06
     عليها
    -0.06
    ，大
    -0.06
     ¦
    -0.06
    art
    -0.06
    entialAction
    -0.05
     Verg
    -0.05
    POSITIVE LOGITS
    �
    0.07
    олнитель
    0.07
     SPELL
    0.06
    _drv
    0.06
     repe
    0.06
    _nf
    0.06
    episode
    0.06
     MODE
    0.06
    349
    0.06
     paramet
    0.06
    Act Density 0.001%

    No Known Activations