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
     Bbw
    -0.07
    τής
    -0.06
    .be
    -0.06
    nob
    -0.06
     nab
    -0.06
     synopsis
    -0.06
    �
    -0.06
    limits
    -0.06
     hardship
    -0.06
    庫
    -0.06
    POSITIVE LOGITS
    ackers
    0.08
     حسب
    0.07
     IMP
    0.06
     tuner
    0.06
     -->↵↵↵
    0.06
    _TOP
    0.06
    ISE
    0.06
     AAP
    0.06
     HOT
    0.06
    -green
    0.06
    Act Density 0.000%

    No Known Activations