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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stagger
    -0.06
    -B
    -0.06
     cleans
    -0.06
     степени
    -0.06
    .bc
    -0.06
    thenReturn
    -0.06
    }")]↵
    -0.06
     strchr
    -0.06
    .k
    -0.06
     authoritative
    -0.06
    POSITIVE LOGITS
     tie
    0.08
    illary
    0.07
    CKER
    0.07
    Falsy
    0.07
     relaxation
    0.07
     disb
    0.06
    	timer
    0.06
     clarification
    0.06
     clin
    0.06
    _velocity
    0.06
    Act Density 0.040%

    No Known Activations