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

    Neuronpedia

    INDEX
    Explanations

    workaround

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pudo
    -0.07
     StringType
    -0.07
    .asset
    -0.06
     spectrum
    -0.06
     spectra
    -0.06
    <Key
    -0.06
     sleepy
    -0.06
     Ras
    -0.06
     fotograf
    -0.06
     ภาพ
    -0.06
    POSITIVE LOGITS
     workaround
    0.11
    ZW
    0.07
    	CG
    0.07
     hack
    0.07
    _SIGN
    0.07
    κι
    0.07
    Audit
    0.07
     حالة
    0.07
    Around
    0.07
    ίγ
    0.07
    Act Density 0.005%

    No Known Activations