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

    Neuronpedia

    INDEX
    Explanations

    strain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Invariant
    -0.07
    .GetType
    -0.07
     instantaneous
    -0.07
    Executable
    -0.07
     PY
    -0.06
     fak
    -0.06
    Nat
    -0.06
    .reflect
    -0.06
    (slice
    -0.06
     Σ
    -0.06
    POSITIVE LOGITS
    	BOOL
    0.07
     كسارة
    0.07
    )))));↵
    0.07
    vpn
    0.06
     });↵↵↵
    0.06
    ellation
    0.06
    )*/↵
    0.06
    captcha
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    bildung
    0.06
    Act Density 0.000%

    No Known Activations